Membership Inference over Diffusion-models-based Synthetic Tabular Data

• URL: http://arxiv.org/abs/2510.16037v1
• Date: Thu, 16 Oct 2025 03:43:11 GMT
• Title: Membership Inference over Diffusion-models-based Synthetic Tabular Data
• Abstract summary: We examine two recent models, TabDDPM and TabSyn, by developing query-based Membership Inference Attacks (MIAs) based on the step-wise error comparison method.<n>Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn, by developing query-based MIAs based on the step-wise error comparison method. Our findings reveal that TabDDPM is more vulnerable to these attacks. TabSyn exhibits resilience against our attack models. Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.

Related papers

• MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data [5.386263643844387]
  Recent developments of diffusion models have been effective on a wide range of data types.<n>Recent developments of diffusion models have been effective on a wide range of data types, but their privacy resilience remains largely unexplored.<n>Recent developments of diffusion models have been effective on a wide range of data types, but their privacy resilience, particularly for formats, remains largely unexplored.
  arXiv  Detail & Related papers  (2026-03-19T17:42:46Z)
• MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data [24.54021019214072]
  We introduce MIAEPT, Membership Inference Attack via Error Prediction for Tabular Data, a novel black-box attack.<n>MIA-EPT constructs errorbased feature vectors by masking and reconstructing attributes of target records.<n>Our results challenge the assumption that synthetic data is inherently privacy-preserving.
  arXiv  Detail & Related papers  (2025-09-16T13:03:54Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Privacy Auditing Synthetic Data Release through Local Likelihood Attacks [7.780592134085148]
  Gene Likelihood Ratio Attack (Gen-LRA)<n>Gen-LRA formulates its attack by evaluating the influence a test observation has in a surrogate model's estimation of a local likelihood ratio over the synthetic data.<n>Results underscore Gen-LRA's effectiveness as a privacy auditing tool for the release of synthetic data.
  arXiv  Detail & Related papers  (2025-08-28T18:27:40Z)
• Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models [51.179816451161635]
  Membership Inference Attacks (MIAs) are designed to ascertain whether specific data were utilized during a model's training phase.<n>We formalize them into a unified general paradigm which computes the membership score for membership identification.<n>Under this paradigm, we empirically find that existing attacks overlook the inherent deficiency in how diffusion models process high-frequency information.<n>We propose a plug-and-play high-frequency filter module to mitigate the adverse effects of the deficiency.
  arXiv  Detail & Related papers  (2025-05-27T09:50:11Z)
• Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis [10.682673935815547]
  Existing privacy evaluations often rely on metrics or weak membership inference attacks (MIA)<n>In this work, we conduct a rigorous MIA study on diffusion-based synthesis, revealing that state-of-the-art attacks designed for image models fail in this setting.<n>Our method, implemented with a lightweight-driven approach, effectively learns membership signals, eliminating the need for manual optimization.
  arXiv  Detail & Related papers  (2025-03-15T06:13:27Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM)<n>To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Privacy Threats in Stable Diffusion Models [0.7366405857677227]
  This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models. MIAs aim to extract sensitive information about a model's training data, posing significant privacy concerns. We devise a black-box MIA that only needs to query the victim model repeatedly.
  arXiv  Detail & Related papers  (2023-11-15T20:31:40Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Synthesizing Mixed-type Electronic Health Records using Diffusion Models [10.973115905786129]
  Synthetic data generation is a promising solution to mitigate privacy concerns when sharing sensitive patient information. Recent studies have shown that diffusion models offer several advantages over GANs, such as generation of more realistic synthetic data and stable training in generating data modalities, including image, text, and sound. Our experiments demonstrate that TabDDPM outperforms the state-of-the-art models across all evaluation metrics, except for privacy, which confirms the trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2023-02-28T15:42:30Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.